{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T06:07:29Z","timestamp":1789106849534,"version":"build-2803163510"},"reference-count":70,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Accurate and efficient automated analysis of Optical Coherence Tomography (OCT) images is critical for large-scale retinal disease screening. However, current deep learning models often fail to simultaneously achieve high classification accuracy, practical computational feasibility, and interpretability. To deal with these problems, this paper presents a deep learning framework on YOLOv11 for eight-class retinal disease classification optimized using a two-stage optimization strategy. The proposed architecture incorporates a Progressive Spatial Fusion (PSF) module to hierarchically integrate multi-scale feature representations, followed by a Squeeze-and-Excitation (SE)-based dual-attention refinement mechanism that refines disease-discriminative features prior to classification. Evaluated on the OCT-C8 dataset, the proposed model achieves 98.00% accuracy, precision, recall, and F1-score, together with 99.70% specificity, while achieving perfect classification performance for the Age-related Macular Degeneration (AMD), Central Serous Retinopathy (CSR), Diabetic Retinopathy (DR), and Macular Hole (MH) classes. Grad-CAM visualizations provide qualitative insights into image regions influencing model predictions and show correspondence with disease-associated structural patterns reported in OCT literature. These results show that the proposed framework provides a good trade-off between classification performance, computational requirements and interpretability and shows potential for automated OCT-based retinal disease screening support.<\/jats:p>","DOI":"10.3389\/frai.2026.1925302","type":"journal-article","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T05:29:24Z","timestamp":1789104564000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A two-stage deep learning framework with progressive feature fusion and attention mechanisms for multi-class retinal disease classification"],"prefix":"10.3389","volume":"9","author":[{"given":"Mithun","family":"Vijayan","sequence":"first","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Vellore, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Goutham","family":"Veerapu","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Vellore, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nisha","family":"J. S.","sequence":"additional","affiliation":[{"name":"Computer Science Engineering, Indian Institute of Information Technology","place":["Kottayam, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"6193","DOI":"10.1038\/s41598-025-89831-2","article-title":"Reinforcement-based leveraging transfer learning for multiclass optical coherence tomography images classification","volume":"15","author":"Abbas","year":"2025","journal-title":"Sci. Rep"},{"key":"B2","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1007\/s10103-024-04089-w","article-title":"Automated classification of choroidal neovascularization, diabetic macular edema, and drusen from retinal OCT images using vision transformers: a comparative study","volume":"39","author":"Ak\u00e7a","year":"2024","journal-title":"Lasers Med. Sci"},{"key":"B3","doi-asserted-by":"publisher","first-page":"102059","DOI":"10.1016\/j.inffus.2023.102059","article-title":"Fundus-deepnet: Multi-label deep learning classification system for enhanced detection of multiple ocular diseases through data fusion of fundus images","volume":"102","author":"Al-Fahdawi","year":"2024","journal-title":"Inf. Fusion"},{"key":"B4","doi-asserted-by":"publisher","first-page":"6798","DOI":"10.1038\/s41598-026-38063-z","article-title":"Identification of multiple ocular diseases using a hybrid quantum convolutional neural network with fundus images","volume":"16","author":"Alqassab","year":"2026","journal-title":"Sci. Rep"},{"key":"B5","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s11517-019-02066-y","article-title":"AOCT-NET: a convolutional network automated classification of multiclass retinal diseases using spectral-domain optical coherence tomography images","volume":"58","author":"Alqudah","year":"2020","journal-title":"Med. Biol. Eng. Comput"},{"key":"B6","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/978-3-030-16638-0_3","volume-title":"High Resolution Imaging in Microscopy and Ophthalmology","author":"Aumann","year":"2019"},{"key":"B7","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1186\/s12859-021-04001-1","article-title":"Classification of age-related macular degeneration using convolutional-neural-network-based transfer learning","volume":"22","author":"Chen","year":"2021","journal-title":"BMC Bioinform"},{"key":"B8","doi-asserted-by":"publisher","first-page":"23256","DOI":"10.1109\/JSEN.2021.3108642","article-title":"Automated classification of retinal OCT images using a deep multi-scale fusion CNN","volume":"21","author":"Das","year":"2021","journal-title":"IEEE Sens. J"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"De Fauw","year":"2018","journal-title":"Nat. Med"},{"key":"B10","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.preteyeres.2007.07.005","article-title":"State-of-the-art retinal optical coherence tomography","volume":"27","author":"Drexler","year":"2008","journal-title":"Prog. Retin. Eye Res"},{"key":"B11","doi-asserted-by":"publisher","first-page":"2611","DOI":"10.1016\/j.ophtha.2013.07.042","article-title":"The international vitreomacular traction study group classification of vitreomacular adhesion, traction, and macular hole","volume":"120","author":"Duker","year":"2013","journal-title":"Ophthalmology"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1109\/INCET54531.2022.9824598","author":"Duvvuri","year":"2022","journal-title":"2022 3rd international conference for emerging technology (INCET)"},{"key":"B13","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.bbe.2025.05.002","article-title":"Multi-scale CNN-swin transformer network with boundary supervision for multiclass biomarker segmentation in retinal oct images","volume":"45","author":"Fan","year":"2025","journal-title":"Biocybern. Biomed. Eng"},{"key":"B14","doi-asserted-by":"publisher","first-page":"2732","DOI":"10.1364\/BOE.8.002732","article-title":"Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative amd patients using deep learning and graph search","volume":"8","author":"Fang","year":"2017","journal-title":"Biomed. Opt. Express"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1959","DOI":"10.1109\/TMI.2019.2898414","article-title":"Attention to lesion: Lesion-aware convolutional neural network for retinal optical coherence tomography image classification","volume":"38","author":"Fang","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B16","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1186\/s40537-023-00757-w","article-title":"Automated segmentation of choroidal neovascularization on optical coherence tomography angiography images of neovascular age-related macular degeneration patients based on deep learning","volume":"10","author":"Feng","year":"2023","journal-title":"J. Big Data"},{"key":"B17","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1016\/j.ophtha.2012.10.036","article-title":"Clinical classification of age-related macular degeneration","volume":"120","author":"Ferris III","year":"2013","journal-title":"Ophthalmology"},{"key":"B18","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/978-1-4612-4380-9_6","author":"Fisher","year":"1970","journal-title":"Breakthroughs in Statistics: Methodology and Distribution"},{"key":"B19","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"B20","doi-asserted-by":"publisher","first-page":"7405","DOI":"10.1038\/s41598-024-82812-x","article-title":"Hybrid attention structure preserving network for reconstruction of under-sampled OCT images","volume":"15","author":"Guo","year":"2025","journal-title":"Sci. Rep"},{"key":"B21","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1016\/j.ajo.2008.11.019","article-title":"Comparison of spectral- and time-domain optical coherence tomography for retinal thickness measurements in healthy and diseased eyes","volume":"147","author":"Han","year":"2009","journal-title":"Am. J. Ophthalmol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s10462-024-10736-z","article-title":"A comprehensive review of artificial intelligence models for screening major retinal diseases","volume":"57","author":"Hassan","year":"2024","journal-title":"Artif. Intell. Rev"},{"key":"B23","doi-asserted-by":"publisher","first-page":"3637","DOI":"10.1038\/s41598-023-30853-z","article-title":"An interpretable transformer network for the retinal disease classification using optical coherence tomography","volume":"13","author":"He","year":"2023","journal-title":"Sci. Rep"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.2147\/OPTH.S47987","article-title":"Optical coherence tomography classification of diabetic cystoid macular edema","volume":"7","author":"Helmy","year":"2013","journal-title":"Clin. Ophthalmol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/s42452-025-06565-6","article-title":"Detection of retinal diseases from oct images using a VGG16 and transfer learning","volume":"7","author":"Jaimes","year":"2025","journal-title":"Disc. Appl. Sci"},{"key":"B26","doi-asserted-by":"publisher","first-page":"3571","DOI":"10.2147\/OPTH.S386946","article-title":"Normative data of macular thickness using spectral domain optical coherence tomography for healthy jordanian children","volume":"16","author":"Jammal","year":"2022","journal-title":"Clin. Ophthalmol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"e512","DOI":"10.1111\/aos.14928","article-title":"Multimodal deep learning with feature level fusion for identification of choroidal neovascularization activity in age-related macular degeneration","volume":"100","author":"Jin","year":"2022","journal-title":"Acta Ophthalmol"},{"key":"B28","author":"Jocher","year":"2024"},{"key":"B29","doi-asserted-by":"publisher","first-page":"104176","DOI":"10.1016\/j.bspc.2022.104176","article-title":"Convolution neural networks for optical coherence tomography (OCT) image classification","volume":"79","author":"Karthik","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany","year":"2018","journal-title":"Cell"},{"key":"B31","doi-asserted-by":"publisher","first-page":"3003","DOI":"10.3390\/math12193003","article-title":"OCTNet: A modified multi-scale attention feature fusion network with inceptionv3 for retinal OCT image classification","volume":"12","author":"Khalil","year":"2024","journal-title":"Mathematics"},{"key":"B32","doi-asserted-by":"publisher","first-page":"6706","DOI":"10.3390\/s23156706","article-title":"Optical coherence tomography image classification using hybrid deep learning and ant colony optimization","volume":"23","author":"Khan","year":"2023","journal-title":"Sensors"},{"key":"B33","doi-asserted-by":"publisher","first-page":"13298","DOI":"10.1038\/s41598-019-49816-4","article-title":"Automatic choroidal segmentation in OCT images using supervised deep learning methods","volume":"9","author":"Kugelman","year":"2019","journal-title":"Sci. Rep"},{"key":"B34","doi-asserted-by":"publisher","first-page":"108726","DOI":"10.1016\/j.compbiomed.2024.108726","article-title":"Htc-retina: a hybrid retinal diseases classification model using transformer-convolutional neural network from optical coherence tomography images","volume":"178","author":"Laouarem","year":"2024","journal-title":"Comput. Biol. Med"},{"key":"B35","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/s10792-025-03439-z","article-title":"Enhancing diabetic retinopathy diagnosis: automatic segmentation of hyperreflective foci in OCT via deep learning","volume":"45","author":"Li","year":"2025","journal-title":"Int. Ophthalmol"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106","author":"Lin","year":"2016","journal-title":"2017 IEEE conference on computer vision and pattern recognition (CVPR)"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913","author":"Liu","year":"2018","journal-title":"2018 IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"B38","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1016\/j.media.2011.06.005","article-title":"Automated macular pathology diagnosis in retinal oct images using multi-scale spatial pyramid and local binary patterns in texture and shape encoding","volume":"15","author":"Liu","year":"2011","journal-title":"Med. Image Anal"},{"key":"B39","doi-asserted-by":"publisher","first-page":"161","DOI":"10.5114\/reum\/166296","article-title":"Subclinical retinopathy in systemic lupus erythematosus patients \u2013 optical coherence tomography study","volume":"61","author":"Mimier-Janczak","year":"2023","journal-title":"Reumatologia"},{"key":"B40","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/s42979-022-01024-0","article-title":"Macularnet: towards fully automated attention-based deep CNN for macular disease classification","volume":"3","author":"Mishra","year":"2022","journal-title":"SN Comput. Sci"},{"key":"B41","unstructured":"Mooney\n              P.\n            \n          \n          Retinal oct images (optical coherence tomography)\n          \n          2018"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1376","DOI":"10.1049\/ipr2.12415","article-title":"Bam: Block attention mechanism for OCT image classification","volume":"16","author":"Nabijiang","year":"2022","journal-title":"IET Image Process"},{"key":"B43","author":"Naren","year":"2021","journal-title":"Retinal OCT image classification"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1109\/ICICOS.2018.8621687","author":"Nugroho","year":"2018","journal-title":"2018 2nd international conference on informatics and computational sciences (ICICoS)"},{"key":"B45","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1016\/S0002-9394(99)00033-1","article-title":"Patterns of diabetic macular edema with optical coherence tomography","volume":"127","author":"Otani","year":"1999","journal-title":"Am. J. Ophthalmol"},{"key":"B46","doi-asserted-by":"publisher","first-page":"107146","DOI":"10.1016\/j.bspc.2024.107146","article-title":"A lightweight model for the retinal disease classification using optical coherence tomography","volume":"101","author":"Pan","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1177\/11206721231210753","article-title":"OCT biomarkers for early prognosis in diabetic macular edema treatment with ranibizumab","volume":"34","author":"Pessoa","year":"2024","journal-title":"Eur. J. Ophthalmol"},{"key":"B48","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.ins.2018.01.051","article-title":"Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images","volume":"441","author":"Raghavendra","year":"2018","journal-title":"Inf. Sci"},{"key":"B49","doi-asserted-by":"publisher","first-page":"1024","DOI":"10.1109\/TMI.2017.2780115","article-title":"Macular OCT classification using a multi-scale convolutional neural network ensemble","volume":"37","author":"Rasti","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B50","doi-asserted-by":"publisher","first-page":"105419","DOI":"10.1016\/j.imavis.2025.105419","article-title":"Grad-CAM based explanations for multiocular disease detection using xceptionnet","volume":"154","author":"Raveenthini","year":"2025","journal-title":"Image Vis. Comput"},{"key":"B51","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1016\/j.ophtha.2017.09.028","article-title":"Consensus definition for atrophy associated with age-related macular degeneration on oct: classification of atrophy report 3","volume":"125","author":"Sadda","year":"2018","journal-title":"Ophthalmology"},{"key":"B52","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1016\/j.ophtha.2005.12.020","article-title":"Automated detection of clinically significant macular edema by grid scanning optical coherence tomography","volume":"113","author":"Sadda","year":"2006","journal-title":"Ophthalmology"},{"key":"B53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10384-022-00943-y","article-title":"Differentiating drusen and drusenoid deposits subtypes on multimodal imaging and risk of advanced age-related macular degeneration","volume":"67","author":"Sakurada","year":"2023","journal-title":"Jpn. J. Ophthalmol"},{"key":"B54","volume-title":"Encyclopedia of Machine Learning","author":"Sammut","year":"2011"},{"key":"B55","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1016\/j.ajo.2015.05.008","article-title":"Identification of drusen characteristics in age-related macular degeneration by polarization-sensitive optical coherence tomography","volume":"160","author":"Schlanitz","year":"2015","journal-title":"Am. J. Ophthalmol"},{"key":"B56","doi-asserted-by":"publisher","first-page":"1144","DOI":"10.1136\/bjophthalmol-2014-305702","article-title":"Guidelines for the management of neovascular age-related macular degeneration by the european society of retina specialists (euretina)","volume":"98","author":"Schmidt-Erfurth","year":"2014","journal-title":"Br. J. Ophthalmol"},{"key":"B57","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/SPICES62143.2024.10779801","article-title":"\u201cClassification of indian medicinal plant species using attention module with transfer learning,\u201d?","author":"Sivappriya","year":"2024","journal-title":"2024 IEEE international conference on signal processing, informatics, communication and energy systems (SPICES)"},{"key":"B58","doi-asserted-by":"publisher","first-page":"1609","DOI":"10.1097\/IAE.0b013e3182247535","article-title":"Anatomical correlates to the bands seen in the outer retina by optical coherence tomography: literature review and model","volume":"31","author":"Spaide","year":"2011","journal-title":"Retina"},{"key":"B59","doi-asserted-by":"publisher","first-page":"105877","DOI":"10.1016\/j.cmpb.2020.105877","article-title":"OctNet: a lightweight CNN for retinal disease classification from optical coherence tomography images","volume":"200","author":"Sunija","year":"2021","journal-title":"Comput. Methods Programs Biomed"},{"key":"B60","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1186\/s12886-020-01382-4","article-title":"Classification of optical coherence tomography images using a capsule network","volume":"20","author":"Tsuji","year":"2020","journal-title":"BMC Ophthalmol"},{"key":"B61","doi-asserted-by":"publisher","first-page":"e13232","DOI":"10.1111\/exsy.13232","article-title":"A deep feature fusion and selection-based retinal eye disease detection from OCT images","volume":"40","author":"Umer","year":"2023","journal-title":"Expert Syst"},{"key":"B62","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s40942-024-00526-8","article-title":"Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography","volume":"10","author":"Valentim","year":"2024","journal-title":"Int. J. Retina Vitr"},{"key":"B63","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3329106","article-title":"OCTformer: an efficient hierarchical transformer network specialized for retinal optical coherence tomography image recognition","volume":"72","author":"Wang","year":"2023","journal-title":"IEEE Trans. Instrum. Meas"},{"key":"B64","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1016\/S0161-6420(03)00475-5","article-title":"Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales","volume":"110","author":"Wilkinson","year":"2003","journal-title":"Ophthalmology"},{"key":"B65","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1111\/aos.12779","article-title":"Central serous chorioretinopathy: what we have learnt so far","volume":"94","author":"Wong","year":"2016","journal-title":"Acta Ophthalmol"},{"key":"B66","year":"2023","journal-title":"Blindness and visual impairment"},{"key":"B67","doi-asserted-by":"publisher","first-page":"100245","DOI":"10.1016\/j.xops.2022.100245","article-title":"Deep-learning-aided diagnosis of diabetic retinopathy, age-related macular degeneration, and glaucoma based on structural and angiographic OCT","volume":"3","author":"Zang","year":"2023","journal-title":"Ophthalmol. Sci"},{"key":"B68","doi-asserted-by":"publisher","first-page":"e28759","DOI":"10.1016\/j.heliyon.2024.e29334","article-title":"Multimodal deep transfer learning to predict retinal vein occlusion macular edema recurrence after anti-vegf therapy","volume":"10","author":"Zhang","year":"2024","journal-title":"Heliyon"},{"key":"B69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40123-025-01209-9","article-title":"Research progress in artificial intelligence for central serous chorioretinopathy: a systematic review","volume":"14","author":"Zhang","year":"2025","journal-title":"Ophthalmol. Ther"},{"key":"B70","first-page":"8792","author":"Zhang","year":"2018","journal-title":"Advances in neural information processing systems"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1925302\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T05:29:26Z","timestamp":1789104566000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1925302\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,11]]},"references-count":70,"alternative-id":["10.3389\/frai.2026.1925302"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1925302","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,11]]},"article-number":"1925302"}}